JoshuaLam21/vision-reader

给无图像能力的 LLM 的看图工具:像素+坐标 → 文本(chunk 概览/裁剪编码/OCR/MCP server)

0Stars on the repository
2Mods indexed here, across every type
27d agoLast push, which is what freshness is scored on
noneNo LICENSE: all rights reserved, so bodies are not copied

vision-reader

01

JoshuaLam21/vision-reader

Skill Claude CodeCodex

An image-analysis skill for models that cannot normally view images. It reads screenshots, documents, charts, and user interfaces, including text found through OCR, which means turning text in an image into editable words.

0 27d ago A 61 tokens